Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+optimizer.pt filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "RetNetModelWithLMHead"
+  ],
+  "chunk_size": 512,
+  "eos_token_id": 0,
+  "ffn_proj_size": 4096,
+  "forward_impl": "parallel",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "is_decoder": true,
+  "model_type": "retnet",
+  "num_heads": 8,
+  "num_layers": 24,
+  "output_retentions": false,
+  "pad_token_id": 0,
+  "qk_dim": 2048,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "unk_token_id": 0,
+  "use_bias_in_mlp": true,
+  "use_bias_in_msr": false,
+  "use_bias_in_msr_out": false,
+  "use_cache": true,
+  "use_default_gamma": false,
+  "v_dim": 4096,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb34afd39768ba1597e6ad2a6041c7d5a2b46e84c85d390bb616c93dbffc084e
+size 5357702585

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916705204d9d7b23393a4710c7c5fc1da5a4824d7896d026b957c57bdb08fdce
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17477db1899efbb56948c9898bcc7fb1e26e601f293d5f0d787777fba1be52a2
+size 627

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "<unk>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be54af290d93c113bcbf421115ae9eed9d6340408f564898f1e966dc738ef01
+size 1136699

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "baichuan-inc/baichuan-7B--tokenization_baichuan.BaiChuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaiChuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,271 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0001555625,
+  "eval_steps": 500,
+  "global_step": 21000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.995e-05,
+      "loss": 3.1324,
+      "step": 500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.99e-05,
+      "loss": 2.7883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9850000000000006e-05,
+      "loss": 2.576,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 2.5156,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.975e-05,
+      "loss": 2.4018,
+      "step": 2500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.97e-05,
+      "loss": 2.3792,
+      "step": 3000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.965e-05,
+      "loss": 2.3919,
+      "step": 3500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.96e-05,
+      "loss": 2.2942,
+      "step": 4000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9550000000000005e-05,
+      "loss": 2.2954,
+      "step": 4500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 2.2145,
+      "step": 5000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.945e-05,
+      "loss": 2.1963,
+      "step": 5500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.94e-05,
+      "loss": 2.218,
+      "step": 6000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.935e-05,
+      "loss": 2.1342,
+      "step": 6500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.93e-05,
+      "loss": 2.1712,
+      "step": 7000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9250000000000004e-05,
+      "loss": 2.1653,
+      "step": 7500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.92e-05,
+      "loss": 2.1579,
+      "step": 8000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.915e-05,
+      "loss": 2.1273,
+      "step": 8500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.91e-05,
+      "loss": 2.1075,
+      "step": 9000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.905e-05,
+      "loss": 2.0985,
+      "step": 9500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9e-05,
+      "loss": 2.0555,
+      "step": 10000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.8950000000000004e-05,
+      "loss": 2.0641,
+      "step": 10500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.89e-05,
+      "loss": 2.062,
+      "step": 11000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.885e-05,
+      "loss": 2.0178,
+      "step": 11500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.88e-05,
+      "loss": 2.0227,
+      "step": 12000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.875e-05,
+      "loss": 2.0456,
+      "step": 12500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.87e-05,
+      "loss": 1.9856,
+      "step": 13000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8650000000000003e-05,
+      "loss": 2.0806,
+      "step": 13500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.86e-05,
+      "loss": 1.9999,
+      "step": 14000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.855e-05,
+      "loss": 1.9597,
+      "step": 14500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.85e-05,
+      "loss": 1.9367,
+      "step": 15000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.845e-05,
+      "loss": 1.9949,
+      "step": 15500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8400000000000004e-05,
+      "loss": 1.9795,
+      "step": 16000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.835e-05,
+      "loss": 1.9473,
+      "step": 16500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.83e-05,
+      "loss": 1.949,
+      "step": 17000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.825e-05,
+      "loss": 1.9626,
+      "step": 17500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.82e-05,
+      "loss": 1.9295,
+      "step": 18000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.815e-05,
+      "loss": 1.9425,
+      "step": 18500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8100000000000004e-05,
+      "loss": 1.8936,
+      "step": 19000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.805e-05,
+      "loss": 1.9084,
+      "step": 19500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8e-05,
+      "loss": 1.907,
+      "step": 20000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.795e-05,
+      "loss": 1.8878,
+      "step": 20500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.79e-05,
+      "loss": 1.9235,
+      "step": 21000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 500000,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "total_flos": 9.977612193497088e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118f388e15e7a727e72711f0831209cc112e8e372d22ba30524e803782275dfc
+size 4027